# Memory Bounded Deep Convolutional Networks Source: [Memory Bounded Deep Convolutional Networks]() Collection index: [llms.txt]() Data updated: 2025-10-25T20:02:28.305Z Authors: Maxwell D. Collins, Pushmeet Kohli Published: 2014-12-03T19:08:38.000Z ## Abstract In this work, we investigate the use of sparsity-inducing regularizers during training of Convolution Neural Networks (CNNs). These regularizers encourage that fewer connections in the convolution and fully connected layers take non-zero values and in effect result in sparse connectivity between hidden units in the deep network. This in turn reduces the memory and runtime cost involved in deploying the learned CNNs. We show that training with such regularization can still be performed using stochastic gradient descent implying that it can be used easily in existing codebases. Experimental evaluation of our approach on MNIST, CIFAR, and ImageNet datasets shows that our regularizers can result in dramatic reductions in memory requirements. For instance, when applied on AlexNet, our method can reduce the memory consumption by a factor of four with minimal loss in accuracy. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on ImageNet (test)](): Image Classification; ImageNet (test); Top-1 Acc: not recorded. ## Original sources and implementation [Original paper]() [PDF]()